Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Survey Solutions MCP Server list all questionnaires in the workspace"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Codex-ready local MCP server for Survey Solutions Headquarters workflows.
This package runs as a local stdio MCP server. It lets Codex inspect Survey Solutions servers, manage local connection profiles, run safe read workflows, download and inspect exports, and perform guarded fieldwork/admin actions when the local profile permission level allows it.
Version: 0.2.7
Runtime: Node.js 20+
MCP transport: local stdio
Default profile: mock Survey Solutions server for local testing
Implemented tools: 123
Prompts: 6
Resources: 2
Current target clients: Codex / OpenAI MCP clients and Claude Desktop local MCP
Developed and tested against Survey Solutions Headquarters server version 26.07
Current scope: curated public API surface for Headquarters discovery, fieldwork operations, exports/version workflows, setup helpers, administration, statistics, and modular QC planning.
License: MIT
Related MCP server: wrapmcp
Manage local Survey Solutions connection profiles with suso-mcp.
Warn about duplicate live profiles and provide cleanup commands.
Explain permission modes and recommend the least-permissive mode for a task.
List workspaces, questionnaires, assignments, interviews, users, and export jobs.
Normalize MCP pagination metadata across Survey Solutions endpoints that mix zero-based and one-based offsets.
Start, inspect, download, and summarize export files.
Return race-aware export cancellation envelopes with refreshed job state.
Activate/deactivate web interview mode and create web-link assignments.
Read interview details/history/stats/PDFs.
Add interview comments and perform approval/rejection actions with explicit confirmations.
Run guarded workspace/user/settings admin actions.
Use GraphQL read queries and raw REST escape hatches when explicitly enabled.
Report runtime diagnostics including package version, build timestamp, config path, active profile, and commit SHA when available, with a non-null fallback for source archives.
Guide Codex or Claude Desktop through a named web-test workflow after manual questionnaire import: check/create test users, activate web mode, create a web assignment, and return the link.
get_api_capabilities may report many REST operations from the active Headquarters Swagger/OpenAPI document. This is the standard server REST API description, not an OpenAI-specific spec, and it is useful for both Codex/OpenAI MCP clients and Claude Desktop. Version 0.2.7 keeps curated tools tied to endpoints confirmed in the tested Survey Solutions 26.07 public OpenAPI document, with raw discovery tools available for future documented endpoints.
get_tool_catalog includes requiredEndpoint, availability, verifiedOnCurrentServer, and unavailableReason fields for curated tools backed by a REST endpoint. Use it to distinguish a tool that is unsupported by the connected Headquarters build from a real missing assignment, questionnaire, or user.
Use curated tools first. Raw REST/GraphQL is deliberately gated and should stay disabled for ordinary AI-agent use. Raw API access is useful for advanced endpoint testing, but it does not provide the same guardrails, confirmations, permission explanations, or workflow guidance as curated tools.
Map and calendar wrappers were removed from the curated surface in v0.2.6 because no matching public REST/GraphQL guide or tested 26.07 OpenAPI endpoints were found. If a future Headquarters build documents those operations, use get_api_capabilities, openapi_operation, or guarded raw API testing before adding curated wrappers back.
From a release zip or GitHub checkout:
npm install
npm run build
npm run smoke
npm linkOn Windows, the easiest path is:
install-and-setup.batThat installer checks Node/npm, installs dependencies, builds, runs smoke tests, links the commands, and optionally walks through live Survey Solutions profile setup.
After running the installer once, these helper files provide a neat click-through way to change local runtime settings:
switch-profile.bat: lists profiles, sets the chosen profile as active/default, and tests it.
change-permission.bat: lists profiles, changes a profile permission level, and disables raw API flags when resetting to read_only.
uninstall-mcp.bat: unlinks the global commands, checks for currently running MCP node processes, and shows the Codex/Claude config cleanup steps. It preserves local profiles unless run with -RemoveProfiles.
Restart Codex after adding or changing the MCP config. Also restart Codex after changing the active profile or permission level if the MCP server was already loaded.
After installation, add this MCP server to Codex/OpenAI MCP configuration. In Codex (ChatGPT Desktop), go to Settings > Plugins > MCPs and enter:
{
"mcpServers": {
"survey-solutions": {
"type": "stdio",
"command": "survey-solutions-mcp",
"args": []
}
}
}If your client requires a direct Node path instead of the linked command:
{
"mcpServers": {
"survey-solutions": {
"type": "stdio",
"command": "node",
"args": [
"C:/path/to/survey-solutions-mcp/dist/index.js"
]
}
}
}Do not put Survey Solutions URLs, usernames, passwords, or tokens in the MCP launch config. Store those through the local profile CLI.
Restart Codex after saving or changing the MCP config so it reloads the local server definition.
In Claude Desktop, go to Settings > Developer > Edit Config. This opens claude_desktop_config.json.
Add the Survey Solutions server under mcpServers using the direct Node path:
{
"mcpServers": {
"survey-solutions": {
"command": "node",
"args": [
"C:\\path\\to\\survey-solutions-mcp\\dist\\index.js"
]
}
}
}Replace the path with the folder where this package was extracted. If your config already has other keys such as preferences, keep them and only add the survey-solutions block inside the existing mcpServers object. Claude Desktop does not need the Codex/OpenAI "type": "stdio" field.
Restart Claude Desktop after saving or changing the config so it reloads the local server definition.
Old extracted copies are mostly harmless if Codex and Claude Desktop no longer reference them. They can become confusing if multiple MCP client config entries point at old package folders, because the client may launch stale server versions.
To clean up the global command link and get guided client-config cleanup steps, double-click:
uninstall-mcp.batThe cleanup helper does not delete C:\Users\<you>\.suso-mcp\config.json by default, because that file may contain profiles you want to reuse with the next version. To remove local profile config as well, run:
powershell -ExecutionPolicy Bypass -File .\uninstall-mcp.ps1 -RemoveProfilesList profiles:
suso-mcp profile listTest the built-in mock profile:
suso-mcp profile test mockAdd a live profile with basic auth:
suso-mcp profile add test-server `
--server-url "https://YOUR-SERVER.mysurvey.solutions" `
--workspace "primary" `
--auth basic `
--username "api_user" `
--password "api_password" `
--permission read_onlyAdd a live profile with bearer/token auth:
suso-mcp profile add test-server `
--server-url "https://YOUR-SERVER.mysurvey.solutions" `
--workspace "primary" `
--auth token `
--token "YOUR_TOKEN" `
--permission read_onlySet the active/default profile:
suso-mcp profile set-default test-server
suso-mcp profile test test-serverRemove a duplicate local profile after choosing the canonical one:
suso-mcp profile delete old-profile-name --yesUse the Survey Solutions MCP. Call survey_solutions_orientation, get_tool_catalog, list_profiles, get_mcp_diagnostics, check_connection, and list_questionnaires.The mock profile should work immediately. Switch to a live profile only after suso-mcp profile test <name> succeeds.
Profiles start as read_only. Raise permissions only for the exact action you intend to run:
suso-mcp profile permission test-server fieldwork_write
suso-mcp profile permission test-server admin_write
suso-mcp profile permission test-server read_onlyRaw API access is separately controlled:
suso-mcp profile raw-api test-server enable-get
suso-mcp profile raw-api test-server enable-writes
suso-mcp profile raw-api test-server enable-delete
suso-mcp profile raw-api test-server enable-graphql-mutations
suso-mcp profile raw-api test-server disablenpm install
npm run check
npm run build
npm run audit:openapi
npm run smokeRelease packaging is a plain source package with dist, docs, installer scripts, and user-pack included. The generated zip should exclude node_modules, local .suso-* folders, temporary files, and user config/secrets.
MIT. See LICENSE.
user-pack/README.md: end-user Codex setup and tool list.
user-pack/LOCAL_COMPUTER_SETUP.md: step-by-step Windows setup.
user-pack/TEST_CHECKLIST.md: mock/live/write testing checklist.
docs/WRITE_TOOL_GUARDRAILS.md: permission and write-action safety notes.
docs/MVP_BACKLOG.md: remaining product backlog.
docs/GITHUB_UPLOAD_CHECKLIST.md: first public GitHub upload checklist.
SECURITY.md: credential and raw-API safety notes.
Activate questionnaire-level web interviews through the same HQ endpoint used by Web Interview Settings. Requires fieldwork_write or admin_write permission.
Inputs: questionnaire_identity (required), profile.
apply_hq_auto_approval: Build or run a guarded QC/support workflow.
Inputs: plan (required), confirm_plan_id (required), rules, profile, +4 more.
Apply a prepared feedback batch after explicit approval. Requires fieldwork_write/admin_write and exact batch confirmation.
Inputs: batch (required), confirm_batch_id (required), profile, max_actions.
Approve an interview as supervisor. Requires fieldwork_write or admin_write permission and exact interview ID confirmation. Live mutation; read current status first and expect the returned state/audit fields to vary by Headquarters build.
Inputs: interview_id (required), confirm_interview_id (required), comment, profile.
Archive an assignment. Requires fieldwork_write or admin_write permission.
Inputs: assignment_id (required), confirm_assignment_id (required), profile.
Archive a supervisor or interviewer user. Requires admin_write permission.
Inputs: user_id (required), confirm_user_id (required), profile.
Reassign an assignment to another responsible user. Requires fieldwork_write/admin_write and exact assignment confirmation.
Inputs: responsible (required), assignment_id (required), confirm_assignment_id (required), profile.
Reassign an interview to another responsible user. Requires fieldwork_write/admin_write and exact interview confirmation.
Inputs: interview_id (required), confirm_interview_id (required), comment, profile, +1 more.
Reassign an interview at supervisor level where supported by the active Headquarters build. Requires fieldwork_write/admin_write and exact interview confirmation.
Inputs: interview_id (required), confirm_interview_id (required), comment, profile, +1 more.
Cancel an export job. Requires fieldwork_write or admin_write permission because it changes server job state.
Inputs: job_id (required), confirm_job_id (required), profile.
Change assignment quantity. Requires fieldwork_write/admin_write and exact assignment confirmation.
Inputs: quantity (required), assignment_id (required), confirm_assignment_id (required), profile.
Change assignment status. Requires fieldwork_write/admin_write and exact assignment confirmation.
Inputs: status (required), assignment_id (required), confirm_assignment_id (required), comment, +1 more.
Change assignment target area. Requires fieldwork_write/admin_write and exact assignment confirmation.
Inputs: target_area (required), assignment_id (required), confirm_assignment_id (required), profile.
Verify that the selected profile can reach and authenticate with Survey Solutions Headquarters. For the mock profile, returns a mock success result.
Inputs: profile.
Remove the Survey Solutions Headquarters global notice. Requires admin_write permission.
Inputs: profile.
Prepare a version-aware combine plan for already downloaded exports, treating later-added variables as structurally missing in earlier versions.
Inputs: export_paths (required), output_dir.
Post a question-level comment using the OpenAPI questionId format. For roster questions, include roster coordinates in question_id as documented by Survey Solutions. Requires fieldwork_write/admin_write.
Inputs: comment (required), question_id (required), interview_id (required), profile.
Post a question-level comment using a variable name and optional roster vector. Requires fieldwork_write or admin_write permission. This is a live mutation with no automatic idempotency key; read the interview first and use exact interview/variable/roster targeting.
Inputs: comment (required), interview_id (required), variable_name (required), profile, +1 more.
Compare known questionnaire version metadata from Headquarters and summarize version differences visible through the API.
Inputs: questionnaire_id_or_title (required), profile.
Compare schemas for downloaded version exports or available questionnaire metadata.
Inputs: profile, export_paths, questionnaire_id_or_title.
Create a Survey Solutions assignment. Can create open web interview links by setting web_mode true and quantity -1. Requires fieldwork_write or admin_write permission.
Inputs: responsible (required), questionnaire_identity (required), email, profile, +8 more.
Create an external web-interview test link: activate web mode if needed and create an unlimited web assignment.
Inputs: responsible (required), questionnaire_identity (required), profile, comments, +1 more.
Create a supervisor or interviewer user. Requires admin_write permission. Passwords are accepted by the API but should be handled as temporary setup secrets.
Inputs: role (required), password (required), username (required), email, +4 more.
Create a new Survey Solutions workspace. Requires admin_write permission.
Inputs: display_name (required), workspace_name (required), profile.
Deactivate questionnaire-level web interviews. Requires fieldwork_write or admin_write permission and exact questionnaire identity confirmation.
Inputs: questionnaire_identity (required), confirm_questionnaire_identity (required), profile.
Delete an interview where supported by the active Headquarters build. Requires fieldwork_write/admin_write and exact interview confirmation. Use only on throwaway/test cases.
Inputs: interview_id (required), confirm_interview_id (required), comment, profile.
Delete a Survey Solutions workspace. Requires admin_write permission and should only be used for empty/test workspaces after checking workspace status.
Inputs: workspace_name (required), confirm_workspace_name (required), profile.
Return human-readable explanations of MCP permission modes, including what each allows/blocks and risk warnings.
Inputs: include_risks, include_examples.
Disable a Survey Solutions workspace. Requires admin_write permission.
Inputs: workspace_name (required), profile.
Download a completed Survey Solutions export job to a local file path on the MCP host.
Inputs: job_id (required), profile, output_path.
Download the PDF transcript for one interview to a local file path on the MCP host.
Inputs: interview_id (required), profile, output_path.
Set assignment size to collected interviews where supported. Requires fieldwork_write/admin_write and exact assignment confirmation.
Inputs: assignment_id (required), confirm_assignment_id (required), profile.
Enable a disabled Survey Solutions workspace. Requires admin_write permission.
Inputs: workspace_name (required), profile.
Explain whether a tool is blocked by the current permission mode and suggest a CLI command or safer alternatives. For rest_request, distinguishes GET, write, and DELETE raw permissions.
Inputs: tool_name (required), method, profile.
Start exports for one questionnaire in multiple formats.
Inputs: export_types (required), questionnaire_identity (required), profile, output_dir, +1 more.
Start exports for all imported versions of a questionnaire title or ID.
Inputs: questionnaire_id_or_title (required), profile, output_dir, export_type, +1 more.
Start exports for all questionnaire versions in one or more formats and return version-aware combine guidance.
Inputs: questionnaire_id_or_title (required), profile, output_dir, export_type, +2 more.
High-level workflow that starts exports for all versions and returns the combine plan and pending download steps.
Inputs: questionnaire_id_or_title (required), profile, output_dir, export_type, +1 more.
Find interviews with no movement for at least min_days using available updated/history timestamps.
Inputs: status, now_utc, profile, min_days.
Generate a compact fieldwork brief from current read-only fieldwork status.
Inputs: profile.
Generate the bash/PowerShell command a user can run to change a profile's permission mode. The MCP does not silently grant itself more permission.
Inputs: profile (required), target_permission_mode (required).
Generate practical tablet setup instructions from workspace/server/user details.
Inputs: workspace_name (required), profile, interviewer_usernames.
Return the currently active Survey Solutions profile and redacted connection details.
Inputs: no named parameters.
Inspect REST/GraphQL capabilities for the Survey Solutions server. Uses /swagger/v1/swagger.json when available.
Inputs: profile, refresh.
Get details for one Survey Solutions assignment, including web mode state where available.
Inputs: assignment_id (required), profile.
Read audio-recording setting for one assignment.
Inputs: assignment_id (required), profile.
Inspect assignment history/changes where the active Headquarters build exposes assignment history.
Inputs: assignment_id (required), profile.
Read quantity/limit behavior for one assignment.
Inputs: assignment_id (required), profile.
Get status/details for a Survey Solutions export job.
Inputs: job_id (required), profile.
Read the Survey Solutions Headquarters global notice setting.
Inputs: profile.
Get available answer/detail values for one interview by interview ID. Use get_interview_history and get_interview_stats for audit trail, status changes, comments, and operational counts.
Inputs: interview_id (required), profile.
Get interviewer details by exact user ID.
Inputs: user_id (required), profile.
Read interviewer actions/audit log over an optional UTC date window where supported.
Inputs: interviewer_id (required), to_utc, profile, from_utc.
Get audit/history records for one interview, including status changes, answers, comments, and assignment actions returned by the active Headquarters build.
Inputs: interview_id (required), profile.
Get interview-level statistics such as answered/not answered, valid/invalid, comments count, duration, key, status, and web interview URL.
Inputs: interview_id (required), profile.
Return MCP package/runtime diagnostics including package version, process start time, config path, config load time, Node.js version, and active profile. Does not expose secrets.
Inputs: no named parameters.
Show effective permission flags for the active or requested profile.
Inputs: profile.
Get metadata for one imported questionnaire/version by GUID$Version identity.
Inputs: questionnaire_identity (required), profile.
Read questionnaire audio-recording settings where supported by the active Headquarters build.
Inputs: questionnaire_identity (required), profile.
Read questionnaire criticality settings where supported by the active Headquarters build.
Inputs: questionnaire_identity (required), profile.
Retrieve questionnaire document/design metadata where the active Headquarters build exposes it.
Inputs: questionnaire_identity (required), profile.
Check whether questionnaire-level web interview mode is active. If inactive, web assignment links may show as expired.
Inputs: questionnaire_identity (required), profile.
Fetch basic Survey Solutions server information and capability summary for the active profile. The surveySolutionsHeader value, when present, is the server's x-survey-solutions response header and usually identifies the Headquarters application/build version.
Inputs: profile.
Read a built-in Survey Solutions statistics report using query parameters.
Inputs: query, profile.
Get supervisor details by exact user ID.
Inputs: user_id (required), profile.
Return an agent-facing catalog of all MCP tools with permission requirement, side effect class, confirmation requirement, mock support, required REST endpoint, and current-server availability when OpenAPI is available.
Inputs: profile, category, permission, side_effect, +3 more.
Get details for a supervisor or interviewer user by ID.
Inputs: user_id (required), profile.
Check whether a workspace can be deleted and inspect blocking counts before deletion.
Inputs: workspace_name (required), profile.
Run a Survey Solutions GraphQL query. Read-only queries are allowed; mutations require raw_api permission and allowRawGraphqlMutations.
Inputs: query (required), profile, variables.
Approve an interview as Headquarters. Requires fieldwork_write or admin_write permission and exact interview ID confirmation. Live mutation; read current status first and expect the returned state/audit fields to vary by Headquarters build.
Inputs: interview_id (required), confirm_interview_id (required), comment, profile.
Reject an interview as Headquarters. Requires fieldwork_write or admin_write permission and exact interview ID confirmation. Live mutation; include a clear comment and read current status first.
Inputs: interview_id (required), confirm_interview_id (required), comment, profile, +1 more.
Move an HQ-approved interview out of HQ approved state. Requires fieldwork_write or admin_write permission and exact interview ID confirmation. Live mutation; read current status first and use only on a known target case.
Inputs: interview_id (required), confirm_interview_id (required), comment, profile.
Inspect a downloaded Survey Solutions export zip on the MCP host. Lists files, classifies data/comment/action/DDI/preview files, and samples lightweight text/tabular metadata without parsing binary Stata/SPSS data.
Inputs: export_path (required), extract, output_dir, sample_rows, +3 more.
Gather read-only evidence around an interviewer anomaly using interviews, assignments, and available action logs.
Inputs: interviewer_id (required), issue_description (required), to_utc, profile, +1 more.
List Survey Solutions assignments. Assignments define responsible users, identifying data, quantities, and rules used to create interviews.
Inputs: limit, query, offset, profile.
List Survey Solutions export jobs for the active workspace. Exports are asynchronous: start a job, poll status, then download the file.
Inputs: profile.
List Survey Solutions interviews using the active workspace interview list endpoint. Interviews are collected or in-progress cases with ID/key/status/responsible user and history; available filters depend on the Headquarters build.
Inputs: limit, query, offset, status, +2 more.
Return canonical Survey Solutions interview status names used by export/status filters and fieldwork workflows.
Inputs: no named parameters.
List configured Survey Solutions profiles. Secrets are never returned.
Inputs: no named parameters.
List imported questionnaires and versions. Questionnaire versioning matters because fieldwork changes create new versions with different schemas.
Inputs: profile.
List questionnaire options available to Survey Solutions statistics reporting.
Inputs: profile.
List questions available to Survey Solutions statistics reporting for a questionnaire. Uses the 26.07 OpenAPI statistics questions endpoint with questionnaireId/version query parameters.
Inputs: questionnaire_identity (required), profile.
List interviewers assigned to a supervisor.
Inputs: supervisor_id (required), limit, query, offset, +1 more.
List active supervisors in the workspace.
Inputs: limit, query, offset, profile.
List Survey Solutions workspaces available to the configured API user. Workspaces are logical areas inside Headquarters, often one per project.
Inputs: profile.
Execute a REST operation by method/path after checking API capabilities. Curated escape hatch with the same raw API permission rules as rest_request for writes.
Inputs: path (required), method (required), body, query, +2 more.
plan_hq_auto_approval: Build or run a guarded QC/support workflow.
Inputs: plan, rules, profile, variables, +4 more.
Prepare human-in-the-loop instructions for importing a questionnaire from Designer into Headquarters when no public import API is available.
Inputs: workspace_name (required), profile, import_comment, questionnaire_name, +1 more.
High-level workflow: start an export for one questionnaire and return export job/download next steps.
Inputs: questionnaire_identity (required), profile, export_type, output_path, +1 more.
Convert a structured issue list into a dry-run feedback batch. Does not write to Survey Solutions.
Inputs: issues (required), profile, default_action.
qc_comment_theme_summary: Summarize comment themes without exposing unnecessary free text.
Inputs: plan, rules, profile, variables, +4 more.
qc_duplicate_records: Flag duplicate interview IDs or duplicate combinations of user-supplied identifying variables.
Inputs: plan, rules, profile, variables, +4 more.
qc_generate_check_plan: Build or run a guarded QC/support workflow.
Inputs: plan, rules, profile, variables, +4 more.
qc_gps_accuracy_and_area: Flag low GPS accuracy or coordinates outside expected areas.
Inputs: plan, rules, profile, variables, +4 more.
qc_gps_duplicates_and_clusters: Flag repeated or tightly clustered GPS points across interviews.
Inputs: plan, rules, profile, variables, +4 more.
qc_heaping_round_numbers: Flag numeric heaping such as excessive 0/5/10 endings.
Inputs: plan, rules, profile, variables, +4 more.
qc_intervention_followup: Compare post-feedback outcomes for targeted interviewers, variables, or cases.
Inputs: plan, rules, profile, variables, +4 more.
qc_interview_duration: Flag unusually short or long interviews using duration fields from Tabular data or duration events from Paradata.
Inputs: plan, rules, profile, variables, +4 more.
qc_logical_consistency: Apply user-supplied logical rules across variables.
Inputs: plan, rules, profile, variables, +4 more.
qc_nonresponse_by_enumerator: Compare missing/nonresponse rates across interviewers.
Inputs: plan, rules, profile, variables, +4 more.
qc_response_distribution_shift: Compare response distributions across interviewers, dates, areas, or versions.
Inputs: plan, rules, profile, variables, +4 more.
qc_roster_consistency: Check roster counts and nested roster relationships for internal consistency.
Inputs: plan, rules, profile, variables, +4 more.
qc_straightlining: Flag repeated identical answers across selected ordinal/categorical variables.
Inputs: plan, rules, profile, variables, +4 more.
qc_submission_timing_bursts: Flag suspicious bursts of submissions or very short gaps between submissions.
Inputs: plan, rules, profile, variables, +4 more.
qc_targeted_missingness: Flag missingness in specific high-priority variables or sections.
Inputs: plan, rules, profile, variables, +4 more.
Recommend the least-permissive permission mode for a described task, e.g. export data, reject interviews, create users, or call raw API endpoints.
Inputs: task_description (required), profile.
Reject an interview as supervisor. Requires fieldwork_write or admin_write permission and exact interview ID confirmation. Live mutation; include a clear comment and read current status first.
Inputs: interview_id (required), confirm_interview_id (required), comment, profile, +1 more.
Advanced raw REST escape hatch. Read-only GET is allowed by default when raw API is enabled. Writes/deletes require explicit raw permission flags.
Inputs: path (required), method (required), body, query, +1 more.
Switch the active profile for this MCP server's local config. This writes local configuration but does not change credentials, permissions, or Survey Solutions server data.
Inputs: profile (required).
Set assignment audio-recording flag. Requires fieldwork_write/admin_write and exact assignment confirmation.
Inputs: enabled (required), assignment_id (required), confirm_assignment_id (required), profile.
Set the Survey Solutions Headquarters global notice. Requires admin_write permission.
Inputs: message (required), profile.
Set questionnaire audio-recording settings. Requires admin_write permission and exact questionnaire identity confirmation.
Inputs: enabled (required), questionnaire_identity (required), confirm_questionnaire_identity (required), profile.
Set questionnaire criticality settings. Requires admin_write permission and exact questionnaire identity confirmation.
Inputs: criticality_level (required), questionnaire_identity (required), confirm_questionnaire_identity (required), profile.
Plan or perform guarded setup for a fieldwork project: workspace, manual Designer import, users, and first web-test assignment.
Inputs: workspace_name (required), users, dry_run, profile, +2 more.
Start a Survey Solutions export job for a questionnaire identity such as GUID$Version. Export creation is allowed in read_only mode because it does not alter fieldwork data.
Inputs: questionnaire_identity (required), to_utc, profile, from_utc, +4 more.
Create a first structural QC summary from a downloaded Survey Solutions export zip: expected file roles, DDI sample variables, readable tabular row/column counts, fieldwork signals, support files, warnings, and next steps. Does not yet parse binary Stata/SPSS values.
Inputs: export_path (required), sample_rows, max_text_bytes.
High-level read-only fieldwork summary over questionnaires, assignments, interviews, and users.
Inputs: profile.
summarize_hq_review_queue: Build or run a guarded QC/support workflow.
Inputs: plan, rules, profile, variables, +4 more.
Summarize interview counts/statuses for one or more interviewers from available interview list data.
Inputs: to_utc, profile, from_utc, interviewer_ids.
Explain Survey Solutions concepts and safe MCP usage: workspaces, questionnaire versions, assignments, interviews, statuses, comments, roster vectors, exports, and permissions.
Inputs: detail_level, include_examples.
Unarchive an assignment. Requires fieldwork_write or admin_write permission.
Inputs: assignment_id (required), profile.
Unarchive a supervisor or interviewer user. Requires admin_write permission.
Inputs: user_id (required), profile.
Update a workspace display name. Requires admin_write permission.
Inputs: display_name (required), workspace_name (required), profile.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 123 tools
Several tools are nearly indistinguishable: multiple export/combine workflow wrappers overlap heavily, and at least four tools (qc_generate_check_plan, plan_hq_auto_approval, apply_hq_auto_approval, summarize_hq_review_queue) share the identical description 'Build or run a guarded QC/support workflow.' An agent selecting between these will frequently pick the wrong one.
The vast majority of tool names follow a consistent snake_case verb-first or domain-prefixed pattern (list_, create_, get_, set_, qc_, etc.). Minor deviations exist, such as noun-style names like survey_solutions_orientation, openapi_operation, and rest_request, but the overall pattern is readable and predictable.
At 123 tools, this server vastly exceeds any reasonable tool surface for an agent to navigate reliably. Many tools are high-level workflow wrappers that overlap with more basic operations, making the count feel padded rather than curated.
The tool set covers an impressively broad lifecycle: workspaces, users, questionnaires, assignments, interviews, exports, QC checks, approvals, and raw API escape hatches. Minor gaps exist, such as no direct user update or questionnaire delete/import endpoint, but those can be worked around via instructions or raw API tools.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server for interacting with the Supabase platform
